activity
20232026
most citedA Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning

1 citations · 2 across the 14 of their papers we have counts for

collaborators
Showing cs.CLShow all

8 papers · 1 filter

cs.CL2026

Where Matters More Than What: Decoding-aligned KV Cache Compression via Position-aware Pseudo Queries

Zhenxu Tian, Yi Su, Juntao Li +1

The Key-Value (KV) cache is crucial for efficient Large Language Models (LLMs) inference, but excessively long contexts drastically increase KV cache memory footprint. Existing KV…

cs.CL2026

MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models

Zecheng Tang, Baibei Ji, Ruoxi Sun +7

Existing works increasingly adopt memory-centric mechanisms to process long contexts in a segment manner, and effective memory management is one of the key capabilities that enable…

cs.CL2025

Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models

Yang Xiang, Yixin Ji, Juntao Li +1

Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning benchmarks. However, their long chain-of-thought reasoning processes incur significant i…

cs.CL2025

Benchmarking Chinese Commonsense Reasoning with a Multi-hop Reasoning Perspective

Wangjie You, Xusheng Wang, Xing Wang +4

While Large Language Models (LLMs) have demonstrated advanced reasoning capabilities, their comprehensive evaluation in general Chinese-language contexts remains understudied. To b…

cs.CL2025

Efficient Reasoning for LLMs through Speculative Chain-of-Thought

Jikai Wang, Juntao Li, Jianye Hou +3

Large reasoning language models such as OpenAI-o1 and Deepseek-R1 have recently attracted widespread attention due to their impressive task-solving abilities. However, the enormous…

cs.CL2024

Revealing and Mitigating the Local Pattern Shortcuts of Mamba

Wangjie You, Zecheng Tang, Juntao Li +2

Large language models (LLMs) have advanced significantly due to the attention mechanism, but their quadratic complexity and linear memory demands limit their performance on long-co…